网站名称查询,活动营销,哈尔滨网站关键字优化,女排联赛排名目录
1 简介
1.1 场景介绍
1.2 约束与限制
2 文本转语音
2.1 场景介绍
2.2 约束与限制
2.3 开发步骤
2.4 设置播报策略
2.4.1 设置单词播报方式
2.4.2 设置数字播报策略
2.4.3 插入静音停顿
2.4.4 指定汉字发音
2.5 开发实例
3 语音识别
3.1 场景介绍
3.2 约束…目录
1 简介
1.1 场景介绍
1.2 约束与限制
2 文本转语音
2.1 场景介绍
2.2 约束与限制
2.3 开发步骤
2.4 设置播报策略
2.4.1 设置单词播报方式
2.4.2 设置数字播报策略
2.4.3 插入静音停顿
2.4.4 指定汉字发音
2.5 开发实例
3 语音识别
3.1 场景介绍
3.2 约束与限制
3.3 开发步骤
3.4 开发实例 1 简介
Core Speech Kit基础语音服务集成了语音类基础AI能力包括文本转语音TextToSpeech及语音识别SpeechRecognizer能力便于用户与设备进行互动实现将实时输入的语音与文本之间相互转换。
1.1 场景介绍 文本转语音将一段不超过10000字符的文本合成为语音并进行播报。语音识别将一段音频信息短语音模式不超过60s长语音模式不超过8h转换为文本可以将pcm音频文件或者实时语音转换为文字。 1.2 约束与限制 AI能力 约束 文本转语音 支持的语种类型中文。简体中文、繁体中文、中文语境下的英文支持的音色类型聆小珊女声音色。文本长度不超过10000字符。 语音识别 支持的语种类型中文普通话。支持的模型类型离线。语音时长短语音模式不超过60s长语音模式不超过8h。
2 文本转语音
Core Speech Kit支持将一篇不超过10000字符的中文文本简体中文、繁体中文、数字、中文语境下的英文合成为语音并以聆小珊女声音色中文播报。
开发者可对播报的策略进行设置包括单词播报、数字播报、静音停顿、汉字发音策略。
2.1 场景介绍
手机/平板等设备在无网状态下系统应用无障碍屏幕朗读接入文本转语音能力为视障人士或不方便阅读场景提供播报能力。
2.2 约束与限制
该能力当前不支持模拟器。
2.3 开发步骤
1. 在使用文本转语音时将实现文本转语音相关的类添加至工程。
import { textToSpeech } from kit.CoreSpeechKit;
import { BusinessError } from kit.BasicServicesKit;2. 调用createEngine接口创建textToSpeechEngine实例。createEngine接口提供了两种调用形式当前以其中一种作为示例其他方式可参考API参考。
let ttsEngine: textToSpeech.TextToSpeechEngine;// 设置创建引擎参数
let extraParam: Recordstring, Object {style: interaction-broadcast, locate: CN, name: EngineName};
let initParamsInfo: textToSpeech.CreateEngineParams {language: zh-CN,person: 0,online: 1,extraParams: extraParam
};// 调用createEngine方法
textToSpeech.createEngine(initParamsInfo, (err: BusinessError, textToSpeechEngine: textToSpeech.TextToSpeechEngine) {if (!err) {console.info(Succeeded in creating engine);// 接收创建引擎的实例ttsEngine textToSpeechEngine;} else {console.error(Failed to create engine. Code: ${err.code}, message: ${err.message}.);}
});3. 得到TextToSpeechEngine实例对象后实例化SpeakParams对象、SpeakListener对象并传入待合成及播报的文本originalText调用speak接口进行播报。
// 设置speak的回调信息
let speakListener: textToSpeech.SpeakListener {// 开始播报回调onStart(requestId: string, response: textToSpeech.StartResponse) {console.info(onStart, requestId: ${requestId} response: ${JSON.stringify(response)});},// 合成完成及播报完成回调onComplete(requestId: string, response: textToSpeech.CompleteResponse) {console.info(onComplete, requestId: ${requestId} response: ${JSON.stringify(response)});},// 停止播报回调onStop(requestId: string, response: textToSpeech.StopResponse) {console.info(onStop, requestId: ${requestId} response: ${JSON.stringify(response)});},// 返回音频流onData(requestId: string, audio: ArrayBuffer, response: textToSpeech.SynthesisResponse) {console.info(onData, requestId: ${requestId} sequence: ${JSON.stringify(response)} audio: ${JSON.stringify(audio)});},// 错误回调onError(requestId: string, errorCode: number, errorMessage: string) {console.error(onError, requestId: ${requestId} errorCode: ${errorCode} errorMessage: ${errorMessage});}
};
// 设置回调
ttsEngine.setListener(speakListener);
let originalText: string Hello HarmonyOS;
// 设置播报相关参数
let extraParam: Recordstring, Object {queueMode: 0, speed: 1, volume: 2, pitch: 1, languageContext: zh-CN,
audioType: pcm, soundChannel: 3, playType: 1 };
let speakParams: textToSpeech.SpeakParams {requestId: 123456, // requestId在同一实例内仅能用一次请勿重复设置extraParams: extraParam
};
// 调用播报方法
// 开发者可以通过修改speakParams主动设置播报策略
ttsEngine.speak(originalText, speakParams);
4. 可选当需要停止合成及播报时可调用stop接口。
ttsEngine.stop();
5. 可选当需要查询文本转语音服务是否处于忙碌状态时可调用isBusy接口。
ttsEngine.isBusy();
6.可选当需要查询支持的语种音色信息时可调用listVoices接口。
listVoices接口提供了两种调用形式当前以其中一种作为示例其他方式可参考API参考。
// 在组件中声明并初始化字符串voiceInfo
State voiceInfo: string ;// 设置查询相关参数
let voicesQuery: textToSpeech.VoiceQuery {requestId: 12345678, // requestId在同一实例内仅能用一次请勿重复设置online: 1
};
// 调用listVoices方法以callback返回
ttsEngine.listVoices(voicesQuery, (err: BusinessError, voiceInfo: textToSpeech.VoiceInfo[]) {if (!err) {// 接收目前支持的语种音色等信息this.voiceInfo JSON.stringify(voiceInfo);console.info(Succeeded in listing voices, voiceInfo is ${this.voiceInfo});} else {console.error(Failed to list voices. Code: ${err.code}, message: ${err.message});}
});
2.4 设置播报策略
由于不同场景下模型自动判断所选择的播报策略可能与实际需求不同此章节提供对于播报策略进行主动设置的方法。 说明 以下取值说明均为有效取值若所使用的数值在有效取值之外则播报结果可能与预期不符并产生错误的播报结果。 2.4.1 设置单词播报方式
文本格式[hN] (N0/1/2)
N取值说明 取值 说明 0 智能判断单词播放方式。默认值为0。 1 逐个字母进行播报。 2 以单词方式进行播报。
文本示例
hello[h1] world
hello使用单词发音world及后续单词将会逐个字母进行发音。
2.4.2 设置数字播报策略
格式[nN] (N0/1/2)
N取值说明 取值 说明 0 智能判断数字处理策略。默认值为0。 1 作为号码逐个数字播报。 2 作为数值播报。超过18位数字不支持自动按逐个数字进行播报。
文本示例
[n2]123[n1]456[n0]
其中123将会按照数值播报456则会按照号码播报而后的文本中的数字均会自动判断
2.4.3 插入静音停顿
格式[pN]
描述N为无符号整数单位为ms。
文本示例
你好[p500]小艺
该句播报时将会在“你好”后插入500ms的静音停顿。
2.4.4 指定汉字发音
汉字声调用后接一位数字1~5分别表示阴平、阳平、上声、去声和轻声5个声调。
格式[MN]
描述M表示拼音N表示声调。
N取值说明 取值 说明 1 阴平 2 阳平 3 上声 4 去声 5 轻声
文本示例
着[zhuo2]手
2.5 开发实例
点击按钮播报一段文本。
import { textToSpeech } from kit.CoreSpeechKit;
import { BusinessError } from kit.BasicServicesKit;let ttsEngine: textToSpeech.TextToSpeechEngine;
Entry
Component
struct Index {State createCount: number 0;State result: boolean false;State voiceInfo: string ;State text: string ;State textContent: string ;State utteranceId: string 123456;State originalText: string \n\t\t古人学问无遗力少壮工夫老始成\n\t\t 纸上得来终觉浅绝知此事要躬行。\n\t\t;State illegalText: string ;build() {Column() {Scroll() {Column() {TextArea({ placeholder: Please enter tts original text, text: ${this.originalText} }).margin(20).focusable(false).border({ width: 5, color: 0x317AE7, radius: 10, style: BorderStyle.Dotted }).onChange((value: string) {this.originalText value;console.info(original text: ${this.originalText});})Button() {Text(CreateEngineByCallback).fontColor(Color.White).fontSize(20)}.type(ButtonType.Capsule).backgroundColor(#0x317AE7).width(80%).height(50).margin(10).onClick(() {this.createCount;console.info(CreateTtsEnginecreateCount:${this.createCount});this.createByCallback();})Button() {Text(speak).fontColor(Color.White).fontSize(20)}.type(ButtonType.Capsule).backgroundColor(#0x317AE7).width(80%).height(50).margin(10).onClick(() {this.createCount;this.speak();})Button() {Text(listVoicesCallback).fontColor(Color.White).fontSize(20)}.type(ButtonType.Capsule).backgroundColor(#0x317AE7).width(80%).height(50).margin(10).onClick(() {this.listVoicesCallback();})Button() {Text(stop).fontColor(Color.White).fontSize(20)}.type(ButtonType.Capsule).backgroundColor(#0x317AE7).width(80%).height(50).margin(10).onClick(() {// 停止播报console.info(Stop button clicked.);ttsEngine.stop();})Button() {Text(isBusy).fontColor(Color.White).fontSize(20)}.type(ButtonType.Capsule).backgroundColor(#0x317AE7).width(80%).height(50).margin(10).onClick(() {// 查询播报状态let isBusy ttsEngine.isBusy();console.info(isBusy: ${isBusy});})Button() {Text(shutdown).fontColor(Color.White).fontSize(20)}.type(ButtonType.Capsule).backgroundColor(#0x317AA7).width(80%).height(50).margin(10).onClick(() {// 释放引擎ttsEngine.shutdown();})}.layoutWeight(1)}.width(100%).height(100%)}}// 创建引擎通过callback形式返回private createByCallback() {// 设置创建引擎参数let extraParam: Recordstring, Object {style: interaction-broadcast, locate: CN, name: EngineName};let initParamsInfo: textToSpeech.CreateEngineParams {language: zh-CN,person: 0,online: 1,extraParams: extraParam};// 调用createEngine方法textToSpeech.createEngine(initParamsInfo, (err: BusinessError, textToSpeechEngine: textToSpeech.TextToSpeechEngine) {if (!err) {console.info(Succeeded in creating engine.);// 接收创建引擎的实例ttsEngine textToSpeechEngine;} else {console.error(Failed to create engine. Code: ${err.code}, message: ${err.message}.);}});};// 调用speak播报方法private speak() {let speakListener: textToSpeech.SpeakListener {// 开始播报回调onStart(requestId: string, response: textToSpeech.StartResponse) {console.info(onStart, requestId: ${requestId} response: ${JSON.stringify(response)});},// 完成播报回调onComplete(requestId: string, response: textToSpeech.CompleteResponse) {console.info(onComplete, requestId: ${requestId} response: ${JSON.stringify(response)});}, // 停止播报完成回调调用stop方法并完成时会触发此回调onStop(requestId: string, response: textToSpeech.StopResponse) {console.info(onStop, requestId: ${requestId} response: ${JSON.stringify(response)});},// 返回音频流onData(requestId: string, audio: ArrayBuffer, response: textToSpeech.SynthesisResponse) {console.info(onData, requestId: ${requestId} sequence: ${JSON.stringify(response)} audio: ${JSON.stringify(audio)});},// 错误回调播报过程发生错误时触发此回调onError(requestId: string, errorCode: number, errorMessage: string) {console.error(onError, requestId: ${requestId} errorCode: ${errorCode} errorMessage: ${errorMessage});}};// 设置回调ttsEngine.setListener(speakListener);// 设置播报相关参数let extraParam: Recordstring, Object {queueMode: 0, speed: 1, volume: 2, pitch: 1, languageContext: zh-CN, audioType: pcm, soundChannel: 3, playType:1}let speakParams: textToSpeech.SpeakParams {requestId: 123456-a, // requestId在同一实例内仅能用一次请勿重复设置extraParams: extraParam};// 调用speak播报方法ttsEngine.speak(this.originalText, speakParams);};// 查询语种音色信息以callback形式返回private listVoicesCallback() {// 设置查询相关参数let voicesQuery: textToSpeech.VoiceQuery {requestId: 123456-b, // requestId在同一实例内仅能用一次请勿重复设置online: 1};// 调用listVoices方法以callback返回语种音色查询结果ttsEngine.listVoices(voicesQuery, (err: BusinessError, voiceInfo: textToSpeech.VoiceInfo[]) {if (!err) {// 接收目前支持的语种音色等信息this.voiceInfo JSON.stringify(voiceInfo);console.info(Succeeded in listing voices, voiceInfo is ${voiceInfo});} else {console.error(Failed to list voices. Code: ${err.code}, message: ${err.message});}});};
}
3 语音识别
将一段中文音频信息中文、中文语境下的英文短语音模式不超过60s长语音模式不超过8h转换为文本音频信息可以为pcm音频文件或者实时语音。
3.1 场景介绍
手机/平板等设备在无网状态下为听障人士或不方便收听音频场景提供音频转文本能力。
3.2 约束与限制
该能力当前不支持模拟器。
3.3 开发步骤
1. 在使用语音识别时将实现语音识别相关的类添加至工程。
import { speechRecognizer } from kit.CoreSpeechKit;
import { BusinessError } from kit.BasicServicesKit;
2. 调用createEngine方法对引擎进行初始化并创建SpeechRecognitionEngine实例。
createEngine方法提供了两种调用形式当前以其中一种作为示例其他方式可参考API参考。
let asrEngine: speechRecognizer.SpeechRecognitionEngine;
let sessionId: string 123456;
// 创建引擎通过callback形式返回
// 设置创建引擎参数
let extraParam: Recordstring, Object {locate: CN, recognizerMode: short};
let initParamsInfo: speechRecognizer.CreateEngineParams {language: zh-CN,online: 1,extraParams: extraParam
};
// 调用createEngine方法
speechRecognizer.createEngine(initParamsInfo, (err: BusinessError, speechRecognitionEngine: speechRecognizer.SpeechRecognitionEngine) {if (!err) {console.info(Succeeded in creating engine.);// 接收创建引擎的实例asrEngine speechRecognitionEngine;} else {console.error(Failed to create engine. Code: ${err.code}, message: ${err.message}.);}
});
3. 得到SpeechRecognitionEngine实例对象后实例化RecognitionListener对象调用setListener方法设置回调用来接收语音识别相关的回调信息。
// 创建回调对象
let setListener: speechRecognizer.RecognitionListener {// 开始识别成功回调onStart(sessionId: string, eventMessage: string) {console.info(onStart, sessionId: ${sessionId} eventMessage: ${eventMessage});},// 事件回调onEvent(sessionId: string, eventCode: number, eventMessage: string) {console.info(onEvent, sessionId: ${sessionId} eventCode: ${eventCode} eventMessage: ${eventMessage});},// 识别结果回调包括中间结果和最终结果onResult(sessionId: string, result: speechRecognizer.SpeechRecognitionResult) {console.info(onResult, sessionId: ${sessionId} sessionId: ${JSON.stringify(result)});},// 识别完成回调onComplete(sessionId: string, eventMessage: string) {console.info(onComplete, sessionId: ${sessionId} eventMessage: ${eventMessage});},// 错误回调错误码通过本方法返回// 如返回错误码1002200006识别引擎正忙引擎正在识别中// 更多错误码请参考错误码参考onError(sessionId: string, errorCode: number, errorMessage: string) {console.error(onError, sessionId: ${sessionId} errorCode: ${errorCode} errorMessage: ${errorMessage});}
}
// 设置回调
asrEngine.setListener(setListener); 4. 分别为音频文件转文字和麦克风转文字功能设置开始识别的相关参数调用startListening方法开始合成。
// 开始识别
private startListeningForWriteAudio() {// 设置开始识别的相关参数let recognizerParams: speechRecognizer.StartParams {sessionId: this.sessionId,audioInfo: { audioType: pcm, sampleRate: 16000, soundChannel: 1, sampleBit: 16 } //audioInfo参数配置请参考AudioInfo}// 调用开始识别方法asrEngine.startListening(recognizerParams);
};private startListeningForRecording() {let audioParam: speechRecognizer.AudioInfo { audioType: pcm, sampleRate: 16000, soundChannel: 1, sampleBit: 16 }let extraParam: Recordstring, Object {recognitionMode: 0,vadBegin: 2000,vadEnd: 3000,maxAudioDuration: 20000}let recognizerParams: speechRecognizer.StartParams {sessionId: this.sessionId,audioInfo: audioParam,extraParams: extraParam}console.info(startListening start);asrEngine.startListening(recognizerParams);
};
5. 传入音频流调用writeAudio方法开始写入音频流。读取音频文件时开发者需预先准备一个pcm格式音频文件。
let uint8Array: Uint8Array new Uint8Array();
// 可以通过如下方式获取音频流1、通过录音获取音频流2、从音频文件中读取音频流
// 2、从音频文件中读取音频流:demo参考
// 写入音频流音频流长度仅支持640或1280
asrEngine.writeAudio(sessionId, uint8Array);
6. 可选当需要查询语音识别服务支持的语种信息可调用listLanguages方法。
listLanguages方法提供了两种调用形式当前以其中一种作为示例其他方式可参考API参考。
// 设置查询相关的参数
let languageQuery: speechRecognizer.LanguageQuery {sessionId: sessionId
};
// 调用listLanguages方法
asrEngine.listLanguages(languageQuery).then((res: Arraystring) {console.info(Succeeded in listing languages, result: ${JSON.stringify(res)}.);
}).catch((err: BusinessError) {console.error(Failed to list languages. Code: ${err.code}, message: ${err.message}.);
});
7. 可选当需要结束识别时可调用finish方法。
// 结束识别
asrEngine.finish(sessionId);
8.可选当需要取消识别时可调用cancel方法。
// 取消识别
asrEngine.cancel(sessionId);
9. 可选当需要释放语音识别引擎资源时可调用shutdown方法。
// 释放识别引擎资源
asrEngine.shutdown();
10. 需要在module.json5配置文件中添加ohos.permission.MICROPHONE权限确保麦克风使用正常。详细步骤可查看声明权限章节。
//...
requestPermissions: [{name : ohos.permission.MICROPHONE,reason: $string:reason,usedScene: {abilities: [EntryAbility],when:inuse}}
],
//...
3.4 开发实例
点击按钮将一段音频信息转换为文本。index.ets文件如下
import { speechRecognizer } from kit.CoreSpeechKit;
import { BusinessError } from kit.BasicServicesKit;
import { fileIo } from kit.CoreFileKit;
import { hilog } from kit.PerformanceAnalysisKit;
import AudioCapturer from ./AudioCapturer;const TAG CoreSpeechKitDemo;let asrEngine: speechRecognizer.SpeechRecognitionEngine;Entry
Component
struct Index {State createCount: number 0;State result: boolean false;State voiceInfo: string ;State sessionId: string 123456;private mAudioCapturer new AudioCapturer();build() {Column() {Scroll() {Column() {Button() {Text(CreateEngineByCallback).fontColor(Color.White).fontSize(20)}.type(ButtonType.Capsule).backgroundColor(#0x317AE7).width(80%).height(50).margin(10).onClick(() {this.createCount;hilog.info(0x0000, TAG, CreateAsrEnginecreateCount:${this.createCount});this.createByCallback();})Button() {Text(setListener).fontColor(Color.White).fontSize(20)}.type(ButtonType.Capsule).backgroundColor(#0x317AE7).width(80%).height(50).margin(10).onClick(() {this.setListener();})Button() {Text(startRecording).fontColor(Color.White).fontSize(20)}.type(ButtonType.Capsule).backgroundColor(#0x317AE7).width(80%).height(50).margin(10).onClick(() {this.startRecording();})Button() {Text(writeAudio).fontColor(Color.White).fontSize(20)}.type(ButtonType.Capsule).backgroundColor(#0x317AE7).width(80%).height(50).margin(10).onClick(() {this.writeAudio();})Button() {Text(queryLanguagesCallback).fontColor(Color.White).fontSize(20)}.type(ButtonType.Capsule).backgroundColor(#0x317AE7).width(80%).height(50).margin(10).onClick(() {this.queryLanguagesCallback();})Button() {Text(finish).fontColor(Color.White).fontSize(20)}.type(ButtonType.Capsule).backgroundColor(#0x317AE7).width(80%).height(50).margin(10).onClick(() {// 结束识别hilog.info(0x0000, TAG, finish click:--);asrEngine.finish(this.sessionId);})Button() {Text(cancel).fontColor(Color.White).fontSize(20)}.type(ButtonType.Capsule).backgroundColor(#0x317AE7).width(80%).height(50).margin(10).onClick(() {// 取消识别hilog.info(0x0000, TAG, cancel click:--);asrEngine.cancel(this.sessionId);})Button() {Text(shutdown).fontColor(Color.White).fontSize(20)}.type(ButtonType.Capsule).backgroundColor(#0x317AA7).width(80%).height(50).margin(10).onClick(() {// 释放引擎asrEngine.shutdown();})}.layoutWeight(1)}.width(100%).height(100%)}}// 创建引擎通过callback形式返回private createByCallback() {// 设置创建引擎参数let extraParam: Recordstring, Object {locate: CN, recognizerMode: short};let initParamsInfo: speechRecognizer.CreateEngineParams {language: zh-CN,online: 1,extraParams: extraParam};// 调用createEngine方法speechRecognizer.createEngine(initParamsInfo, (err: BusinessError, speechRecognitionEngine:speechRecognizer.SpeechRecognitionEngine) {if (!err) {hilog.info(0x0000, TAG, Succeeded in creating engine.);// 接收创建引擎的实例asrEngine speechRecognitionEngine;} else {// 无法创建引擎时返回错误码1002200001原因语种不支持、模式不支持、初始化超时、资源不存在等导致创建引擎失败// 无法创建引擎时返回错误码1002200006原因引擎正在忙碌中一般多个应用同时调用语音识别引擎时触发// 无法创建引擎时返回错误码1002200008原因引擎已被销毁hilog.error(0x0000, TAG, Failed to create engine. Code: ${err.code}, message: ${err.message}.);}});}// 查询语种信息以callback形式返回private queryLanguagesCallback() {// 设置查询相关参数let languageQuery: speechRecognizer.LanguageQuery {sessionId: 123456};// 调用listLanguages方法asrEngine.listLanguages(languageQuery, (err: BusinessError, languages: Arraystring) {if (!err) {// 接收目前支持的语种信息hilog.info(0x0000, TAG, Succeeded in listing languages, result: ${JSON.stringify(languages)});} else {hilog.error(0x0000, TAG, Failed to create engine. Code: ${err.code}, message: ${err.message}.);}});};// 开始识别private startListeningForWriteAudio() {// 设置开始识别的相关参数let recognizerParams: speechRecognizer.StartParams {sessionId: this.sessionId,audioInfo: { audioType: pcm, sampleRate: 16000, soundChannel: 1, sampleBit: 16 } //audioInfo参数配置请参考AudioInfo}// 调用开始识别方法asrEngine.startListening(recognizerParams);};private startListeningForRecording() {let audioParam: speechRecognizer.AudioInfo { audioType: pcm, sampleRate: 16000, soundChannel: 1, sampleBit: 16 }let extraParam: Recordstring, Object {recognitionMode: 0,vadBegin: 2000,vadEnd: 3000,maxAudioDuration: 20000}let recognizerParams: speechRecognizer.StartParams {sessionId: this.sessionId,audioInfo: audioParam,extraParams: extraParam}hilog.info(0x0000, TAG, startListening start);asrEngine.startListening(recognizerParams);};// 写音频流private async writeAudio() {this.startListeningForWriteAudio();hilog.error(0x0000, TAG, Failed to read from file. Code);let ctx getContext(this);let filenames: string[] fileIo.listFileSync(ctx.filesDir);if (filenames.length 0) {hilog.error(0x0000, TAG, Failed to read from file. Code);return;}hilog.error(0x0000, TAG, Failed to read from file. Code);let filePath: string ${ctx.filesDir}/${filenames[0]};let file fileIo.openSync(filePath, fileIo.OpenMode.READ_WRITE);try {let buf: ArrayBuffer new ArrayBuffer(1280);let offset: number 0;while (1280 fileIo.readSync(file.fd, buf, {offset: offset})) {let uint8Array: Uint8Array new Uint8Array(buf);asrEngine.writeAudio(123456, uint8Array);await this.countDownLatch(1);offset offset 1280;}} catch (err) {hilog.error(0x0000, TAG, Failed to read from file. Code: ${err.code}, message: ${err.message}.);} finally {if (null ! file) {fileIo.closeSync(file);}}}// 麦克风语音转文本private async startRecording() {this.startListeningForRecording();// 录音获取音频let data: ArrayBuffer;hilog.info(0x0000, TAG, create capture success);this.mAudioCapturer.init((dataBuffer: ArrayBuffer) {hilog.info(0x0000, TAG, start write);hilog.info(0x0000, TAG, ArrayBuffer JSON.stringify(dataBuffer));data dataBufferlet uint8Array: Uint8Array new Uint8Array(data);hilog.info(0x0000, TAG, ArrayBuffer uint8Array JSON.stringify(uint8Array));// 写入音频流asrEngine.writeAudio(1234567, uint8Array);});};// 计时public async countDownLatch(count: number) {while (count 0) {await this.sleep(40);count--;}}// 睡眠private sleep(ms: number):Promisevoid {return new Promise(resolve setTimeout(resolve, ms));}// 设置回调private setListener() {// 创建回调对象let setListener: speechRecognizer.RecognitionListener {// 开始识别成功回调onStart(sessionId: string, eventMessage: string) {hilog.info(0x0000, TAG, onStart, sessionId: ${sessionId} eventMessage: ${eventMessage});},// 事件回调onEvent(sessionId: string, eventCode: number, eventMessage: string) {hilog.info(0x0000, TAG, onEvent, sessionId: ${sessionId} eventCode: ${eventCode} eventMessage: ${eventMessage});},// 识别结果回调包括中间结果和最终结果onResult(sessionId: string, result: speechRecognizer.SpeechRecognitionResult) {hilog.info(0x0000, TAG, onResult, sessionId: ${sessionId} sessionId: ${JSON.stringify(result)});},// 识别完成回调onComplete(sessionId: string, eventMessage: string) {hilog.info(0x0000, TAG, onComplete, sessionId: ${sessionId} eventMessage: ${eventMessage});},// 错误回调错误码通过本方法返回// 返回错误码1002200002开始识别失败重复启动startListening方法时触发// 更多错误码请参考错误码参考onError(sessionId: string, errorCode: number, errorMessage: string) {hilog.error(0x0000, TAG, onError, sessionId: ${sessionId} errorCode: ${errorCode} errorMessage: ${errorMessage});},}// 设置回调asrEngine.setListener(setListener);};
}
添加AudioCapturer.ts文件用于获取麦克风音频流。
use strict;
/** Copyright (c) Huawei Technologies Co., Ltd. 2023-2023. All rights reserved.*/import {audio} from kit.AudioKit;
import { hilog } from kit.PerformanceAnalysisKit;const TAG AudioCapturer;/*** Audio collector tool*/
export default class AudioCapturer {/*** Collector object*/private mAudioCapturer null;/*** Audio Data Callback Method*/private mDataCallBack: (data: ArrayBuffer) void null;/*** Indicates whether recording data can be obtained.*/private mCanWrite: boolean true;/*** Audio stream information*/private audioStreamInfo {samplingRate: audio.AudioSamplingRate.SAMPLE_RATE_16000,channels: audio.AudioChannel.CHANNEL_1,sampleFormat: audio.AudioSampleFormat.SAMPLE_FORMAT_S16LE,encodingType: audio.AudioEncodingType.ENCODING_TYPE_RAW}/*** Audio collector information*/private audioCapturerInfo {source: audio.SourceType.SOURCE_TYPE_MIC,capturerFlags: 0}/*** Audio Collector Option Information*/private audioCapturerOptions {streamInfo: this.audioStreamInfo,capturerInfo: this.audioCapturerInfo}/*** Initialize* param audioListener*/public async init(dataCallBack: (data: ArrayBuffer) void) {if (null ! this.mAudioCapturer) {hilog.error(0x0000, TAG, AudioCapturerUtil already init);return;}this.mDataCallBack dataCallBack;this.mAudioCapturer await audio.createAudioCapturer(this.audioCapturerOptions).catch(error {hilog.error(0x0000, TAG, AudioCapturerUtil init createAudioCapturer failed, code is ${error.code}, message is ${error.message});});}/*** start recording*/public async start() {hilog.error(0x0000, TAG, AudioCapturerUtil start);let stateGroup [audio.AudioState.STATE_PREPARED, audio.AudioState.STATE_PAUSED, audio.AudioState.STATE_STOPPED];if (stateGroup.indexOf(this.mAudioCapturer.state) -1) {hilog.error(0x0000, TAG, AudioCapturerUtil start failed);return;}this.mCanWrite true;await this.mAudioCapturer.start();while (this.mCanWrite) {let bufferSize await this.mAudioCapturer.getBufferSize();let buffer await this.mAudioCapturer.read(bufferSize, true);this.mDataCallBack(buffer)}}/*** stop recording*/public async stop() {if (this.mAudioCapturer.state ! audio.AudioState.STATE_RUNNING this.mAudioCapturer.state ! audio.AudioState.STATE_PAUSED) {hilog.error(0x0000, TAG, AudioCapturerUtil stop Capturer is not running or paused);return;}this.mCanWrite false;await this.mAudioCapturer.stop();if (this.mAudioCapturer.state audio.AudioState.STATE_STOPPED) {hilog.info(0x0000, TAG, AudioCapturerUtil Capturer stopped);} else {hilog.error(0x0000, TAG, Capturer stop failed);}}/*** release*/public async release() {if (this.mAudioCapturer.state audio.AudioState.STATE_RELEASED || this.mAudioCapturer.state audio.AudioState.STATE_NEW) {hilog.error(0x0000, TAG, Capturer already released);return;}await this.mAudioCapturer.release();this.mAudioCapturer null;if (this.mAudioCapturer.state audio.AudioState.STATE_RELEASED) {hilog.info(0x0000, TAG, Capturer released);} else {hilog.error(0x0000, TAG, Capturer release failed);}}
}
在EntryAbility.ets文件中添加麦克风权限。
import { abilityAccessCtrl, AbilityConstant, UIAbility, Want } from kit.AbilityKit;
import { hilog } from kit.PerformanceAnalysisKit;
import { window } from kit.ArkUI;
import { BusinessError } from kit.BasicServicesKit;export default class EntryAbility extends UIAbility {onCreate(want: Want, launchParam: AbilityConstant.LaunchParam): void {hilog.info(0x0000, testTag, %{public}s, Ability onCreate);}onDestroy(): void {hilog.info(0x0000, testTag, %{public}s, Ability onDestroy);}onWindowStageCreate(windowStage: window.WindowStage): void {// Main window is created, set main page for this abilityhilog.info(0x0000, testTag, %{public}s, Ability onWindowStageCreate);let atManager abilityAccessCtrl.createAtManager();atManager.requestPermissionsFromUser(this.context, [ohos.permission.MICROPHONE]).then((data) {hilog.info(0x0000, testTag, data: JSON.stringify(data));hilog.info(0x0000, testTag, data permissions: data.permissions);hilog.info(0x0000, testTag, data authResults: data.authResults);}).catch((err: BusinessError) {hilog.error(0x0000, testTag, errCode: err.code errMessage: err.message);});windowStage.loadContent(pages/Index, (err, data) {if (err.code) {hilog.error(0x0000, testTag, Failed to load the content. Cause: %{public}s, JSON.stringify(err) ?? );return;}hilog.info(0x0000, testTag, Succeeded in loading the content. Data: %{public}s, JSON.stringify(data) ?? );});}onWindowStageDestroy(): void {// Main window is destroyed, release UI related resourceshilog.info(0x0000, testTag, %{public}s, Ability onWindowStageDestroy);}onForeground(): void {// Ability has brought to foregroundhilog.info(0x0000, testTag, %{public}s, Ability onForeground);}onBackground(): void {// Ability has back to backgroundhilog.info(0x0000, testTag, %{public}s, Ability onBackground);}
}
